1.3k citations · 1.8k across the 13 of their papers we have counts for
15 papers
Pruning Very Deep Neural Network Channels for Efficient Inference
Yihui He
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorith…
Motion Prediction in Visual Object Tracking
Jianren Wang, Yihui He
Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate syste…
Epipolar Transformers
Yihui He, Rui Yan, Katerina Fragkiadaki +1
A common approach to localize 3D human joints in a synchronized and calibrated multi-view setup consists of two-steps: (1) apply a 2D detector separately on each view to localize j…
Deep Mixture Density Network for Probabilistic Object Detection
Yihui He, Jianren Wang
Mistakes/uncertainties in object detection could lead to catastrophes when deploying robots in the real world. In this paper, we measure the uncertainties of object localization to…
Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
Yihui He, Jianing Qian, Jianren Wang +5
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, wh…
MoBiNet: A Mobile Binary Network for Image Classification
Hai Phan, Dang Huynh, Yihui He +2
MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platfo…
Prediction-Tracking-Segmentation
Jianren Wang, Yihui He, Xiaobo Wang +2
We introduce a prediction driven method for visual tracking and segmentation in videos. Instead of solely relying on matching with appearance cues for tracking, we build a predicti…
Feature Selective Anchor-Free Module for Single-Shot Object Detection
Chenchen Zhu, Yihui He, Marios Savvides
We motivate and present feature selective anchor-free (FSAF) module, a simple and effective building block for single-shot object detectors. It can be plugged into single-shot dete…
An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition
Devesh Walawalkar, Yihui He, Rohit Pillai
In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio. Empowered by convolutional neural networks, the…
Shift-based Primitives for Efficient Convolutional Neural Networks
Huasong Zhong, Xianggen Liu, Yihui He +1
We propose a collection of three shift-based primitives for building efficient compact CNN-based networks. These three primitives (channel shift, address shift, shortcut shift) can…
Bounding Box Regression with Uncertainty for Accurate Object Detection
Yihui He, Chenchen Zhu, Jianren Wang +2
Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced…
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Yihui He, Ji Lin, Zhijian Liu +3
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Convention…
Estimated Depth Map Helps Image Classification
Yihui He
We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to gener…
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He, Xiangyu Zhang, Jian Sun
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm…
Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network
Yudong Liang, Ze Yang, Kai Zhang +3
Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual netwo…